INDEX

Explanations

questions and user queries related to technical setups or instructions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 تضيفلها

-1.04

 متعلقه

-0.98

 possano

-0.90

 estekak

-0.90

 CreateTagHelper

-0.89

 fossero

-0.87

 resourceCulture

-0.86

mybatisplus

-0.84

✨:

-0.84

 devront

-0.83

POSITIVE LOGITS

is

0.72

se

0.70

me

0.65

has

0.63

it

0.59

0.58

us

0.51

le

0.51

 не

0.47

 δεν

0.46

Activations Density 0.100%

questions and user queries related to technical setups or instructions

No Comments

No Known Activations